app.py

import os
import streamlit as st
import pickle
import time
from langchain import OpenAI
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import UnstructuredURLLoader
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
openai_api_key = os.getenv('/content/openkey.env')  # Correct the key name to match the environment variable

# Set OpenAI API key
os.environ['OPENAI_API_KEY'] = '/content/openkey.env'

st.title("RockyBot: News Research Tool 📈")
st.sidebar.title("News Article URLs")

urls = []
for i in range(3):
    url = st.sidebar.text_input(f"URL {i+1}")
    urls.append(url)

process_url_clicked = st.sidebar.button("Process URLs")
file_path = "faiss_store_openai.pkl"

main_placeholder = st.empty()
llm = OpenAI(temperature=0.9, max_tokens=500)

if process_url_clicked:
    # Load data
    loader = UnstructuredURLLoader(urls=urls)
    main_placeholder.text("Data Loading...Started...✅✅✅")
    data = loader.load()

    # Split data
    text_splitter = RecursiveCharacterTextSplitter(
        separators=['\n\n', '\n', '.', ','],
        chunk_size=1000
    )
    main_placeholder.text("Text Splitter...Started...✅✅✅")
    docs = text_splitter.split_documents(data)

    # Debugging: Print the number of documents
    print("Number of Documents:", len(docs))

    if docs:
        # Create embeddings and save to FAISS index
        embeddings = OpenAIEmbeddings()
        # Generate embeddings for the documents
        doc_texts = [doc.text for doc in docs]
        embeddings = embeddings.embed(doc_texts)

        # Debugging: Print the number of embeddings
        print("Number of Embeddings:", len(embeddings))

        if embeddings:
            vectorstore_openai = FAISS.from_documents(docs, embeddings)
            main_placeholder.text("Embedding Vector Started Building...✅✅✅")
            time.sleep(2)

            # Save the FAISS index to a pickle file
            with open(file_path, "wb") as f:
                pickle.dump(vectorstore_openai, f)
        else:
            main_placeholder.text("Embedding creation failed. No embeddings found.")
    else:
        main_placeholder.text("Document splitting failed. No documents found.")

query = main_placeholder.text_input("Question: ")
if query:
    if os.path.exists(file_path):
        with open(file_path, "rb") as f:
            vectorstore = pickle.load(f)
            chain = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=vectorstore.as_retriever())
            result = chain({"question": query}, return_only_outputs=True)
            
            # Display the answer
            st.header("Answer")
            st.write(result["answer"])

            # Display sources, if available
            sources = result.get("sources", "")
            if sources:
                st.subheader("Sources:")
                sources_list = sources.split("\n")
                for source in sources_list:
                    st.write(source)